agent-memorylisted
Install: claude install-skill jayzeng/agentmemory
# Agent Memory
You have a persistent memory system. Use it **proactively** — don't wait to be asked.
Pi users can choose the native extension (`pi-memory`: https://github.com/jayzeng/pi-memory) or use this CLI + skill workflow as the cross-platform alternative.
## On Session Start — Load Context First
Run this at the beginning of every session to load your memory:
```bash
agent-memory context --no-search 2>/dev/null
```
This prints your scratchpad, today's log, long-term memory, and yesterday's log. Review it — especially **open scratchpad items** — before starting work.
If the user's task relates to prior work, search for relevant memories:
```bash
agent-memory search --query "<topic>" --mode keyword
```
**Tip:** For project-specific rules (linting, formatting, test conventions), prefer `.cursorrules` or project-level config files. Use agent-memory for cross-project and cross-session knowledge.
## On Session End (After Significant Work)
1. Log what was accomplished in the daily log
2. Mark completed scratchpad items as done; add new follow-ups
3. Only write to long-term memory if you discovered a **durable fact** that doesn't already exist there
## Where to Write — Decision Guide
**Default to daily. Long-term is rare.**
| What happened | Write to | Why |
|---|---|---|
| Made progress, fixed a bug, investigated something | `daily` | Session-specific — searchable later via qmd |
| Tracking a topic or event across days | `topic` | Builds a per-topic file with backl